fix PR4767, a crash because fp stackifier visited blocks in

depth first order, so it wouldn't process unreachable blocks.
When compiling at -O0, late dead block elimination isn't done
and the bad instructions got to isel.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@81187 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 38 insertions, 0 deletions

diff --git a/lib/Target/X86/X86FloatingPoint.cpp b/lib/Target/X86/X86FloatingPoint.cpp
index af0da6fb52..d9a05a83b9 100644
--- a/lib/Target/X86/X86FloatingPoint.cpp
+++ b/lib/Target/X86/X86FloatingPoint.cpp
@@ -213,6 +213,14 @@ bool FPS::runOnMachineFunction(MachineFunction &MF) {
        I != E; ++I)
     Changed |= processBasicBlock(MF, **I);
 
+  // Process any unreachable blocks in arbitrary order now.
+  if (MF.size() == Processed.size())
+    return Changed;
+
+  for (MachineFunction::iterator BB = MF.begin(), E = MF.end(); BB != E; ++BB)
+    if (Processed.insert(BB))
+      Changed |= processBasicBlock(MF, *BB);
+  
   return Changed;
 }
 
diff --git a/test/CodeGen/X86/fp-stack-O0-crash.ll b/test/CodeGen/X86/fp-stack-O0-crash.ll
new file mode 100644
index 0000000000..4768ea2019
--- /dev/null
+++ b/test/CodeGen/X86/fp-stack-O0-crash.ll
@@ -0,0 +1,30 @@
+; RUN: llc %s -O0 -fast-isel -regalloc=local -o -
+; PR4767
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
+target triple = "i386-apple-darwin10"
+
+define void @fn(x86_fp80 %x) nounwind ssp {
+entry:
+  %x.addr = alloca x86_fp80                       ; <x86_fp80*> [#uses=5]
+  store x86_fp80 %x, x86_fp80* %x.addr
+  br i1 false, label %cond.true, label %cond.false
+
+cond.true:                                        ; preds = %entry
+  %tmp = load x86_fp80* %x.addr                   ; <x86_fp80> [#uses=1]
+  %tmp1 = load x86_fp80* %x.addr                  ; <x86_fp80> [#uses=1]
+  %cmp = fcmp oeq x86_fp80 %tmp, %tmp1            ; <i1> [#uses=1]
+  br i1 %cmp, label %if.then, label %if.end
+
+cond.false:                                       ; preds = %entry
+  %tmp2 = load x86_fp80* %x.addr                  ; <x86_fp80> [#uses=1]
+  %tmp3 = load x86_fp80* %x.addr                  ; <x86_fp80> [#uses=1]
+  %cmp4 = fcmp une x86_fp80 %tmp2, %tmp3          ; <i1> [#uses=1]
+  br i1 %cmp4, label %if.then, label %if.end
+
+if.then:                                          ; preds = %cond.false, %cond.true
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %cond.false, %cond.true
+  ret void
+}